About

Assistant Professor of Practice
Department of Computer Science
The George Washington University

Human-Centered AI and Machine Learning for Complex Human Data

I develop artificial intelligence and machine-learning methods for complex human data, with a focus on reliable and interpretable learning across people and real-world settings. My research spans neural and behavioral sensing, EEG-based brain-computer interfaces, multimodal human data, interactive AI systems, and AI for learning.

I previously served as a Visiting Assistant Professor of Computer Science at Swarthmore College. I received my Ph.D. in Computer Science from Brandeis University and my B.S. in Computer Science from Dalian University of Technology.

Research

My research addresses two related problems. First, human data such as neural signals, gaze, behavioral traces, interaction data, and wearable sensing are noisy, temporal, heterogeneous, and often vary across people, sessions, devices, and settings. Second, AI systems increasingly operate in settings where people interact with them, respond to their feedback, and change their behavior.

My goal is to develop models that remain reliable and interpretable across people and settings, and to understand how AI systems behave when people interact with them. EEG and brain-computer interfaces are important testbeds in this work, but the broader questions extend to multimodal sensing, health and neuroscience, interactive AI, and AI for learning.

My group works with undergraduate and graduate students on machine learning, human-centered AI, EEG/BCI, multimodal human data, and AI for learning. I welcome motivated students interested in these areas.

Research Themes

Machine Learning for Complex Human Data

I study machine-learning methods for neural, behavioral, and multimodal human data. These data are often noisy, time-dependent, and variable across people and measurement conditions. My work examines temporal modeling, multimodal learning, generalization across subjects and sessions, model behavior, and failure analysis.

EEG has been an important testbed because it makes these challenges especially visible. Related projects include EEG classification, gaze prediction, sleep EEG, motor imagery, consumer-grade sensing, clinical EEG, and multimodal human data.

Human-Centered and Interactive AI

I study AI systems that people interact with and adapt to over time. My work includes human-in-the-loop BCI, accessible EEG game control, real-time personalization, and other interactive systems that combine machine learning with human feedback.

I am especially interested in how user variation, sensing quality, uncertainty, interface design, and feedback affect system behavior. These questions connect technical model evaluation with the way people actually use AI systems.

AI for Learning and Education

I study how AI affects human reasoning and learning, particularly in computing and higher education. My work has examined generative AI in higher education, AI-supported research and summarization, project-based machine-learning education, EEG markers of learning, and wearable EEG for reading support.

A central question is when AI helps people understand problems, compare alternatives, and develop technical judgment—and when it replaces parts of the reasoning that learners still need to develop.

Publications

Full publication information is available on my Google Scholar and ResearchGate pages.

Machine Learning for Complex Human Data

2026

  • Agentic Feature Selection via LLM for Epileptic Seizure Detection
    Aizierjiang Aiersilan and Xiaodong Qu
    BioNLP 2026, Association for Computational Linguistics [PDF]

  • Human-Centered AI for Sleep EEG: A Systematic Review of Translational and Cross-Species Evidence
    Cole Garrison, Zeina Nweashe, and Xiaodong Qu
    HCI International, 2026 [PDF]

  • A Systematic Review of Consumer-Grade EEG Applications in Directional Game Control via Motor Imagery
    Wensi Xie, Yiran Wang, Sara Dou, and Xiaodong Qu
    HCI International, 2026 [PDF]

  • A Review of Transformer-Based and Hybrid Deep Learning Approaches for EEG Analysis
    Aniket Konkar and Xiaodong Qu
    HCI International, 2026 [PDF]

2025

  • EEG EyeNet: Strong, Insightful Baselines for Eye-Movement Prediction from EEG
    Christian Shun Jin and Xiaodong Qu
    IEEE International Conference on Data Mining Workshops (ICDMW), 2025

  • GViT: Combining Convolutional and Transformer Layers for Spatial-Temporal EEG Analysis
    Chenxu Zhu, Yiming Xu, and Xiaodong Qu
    HCI International, 2025 [PDF]

2024

  • Advancing EEG-Based Gaze Prediction Using Depthwise Separable Convolution and Enhanced Pre-processing
    Matthew L. Key, Tural Mehtiyev, and Xiaodong Qu
    HCI International, 2024 [PDF]

  • Enhancing Eye-Tracking Performance Through Multi-task Learning Transformer
    Weigeng Li, Neng Zhou, and Xiaodong Qu
    HCI International, 2024 [PDF]

2023

2022

2020

Human-Centered and Interactive AI

2026

  • Toward Deployable Neural Directional Control: Design Patterns and Evaluation Challenges
    Cole Garrison, Masih Faryadi, Nawwaf Aleisa, and Xiaodong Qu
    HCI International, 2026 [PDF]

  • Accessible EEG Game Control: Real-Time Personalization with Consumer-Grade EEG Hardware
    Nawwaf Aleisa, Yingzhou Lu, Lifu Gao, Zeina Nweashe, Emily Flanagan, Matthew Winchester, Sylvester Junior Ampomah, and Xiaodong Qu
    HCI International, 2026 [PDF]

2025

  • EMIGC: An EEG Motor Imagery Controller for Real-Time Gameplay
    Yiran Wang, Wensi Xie, Sara Dou, and Xiaodong Qu
    HCI International, 2025 [PDF]

  • From Theory to Play: A Review of EEG-Controlled Directional Games and Evaluation of Custom-Developed BCI Games
    Wensi Xie, Jingwen Dou, Yiran Wang, and Xiaodong Qu
    KDD 2025 Undergraduate and Master’s Consortium [PDF]

  • Amazon-M2 Product Recommendation in Underrepresented Locales Using ChatGPT4o-mini and Gemini Models
    Qicheng Chen and Xiaodong Qu
    HCI International, 2025

  • Human-Centered AI Agents for Healthcare and Education: A Systematic Literature Review
    Lifu Gao, Joshua Sherwood, Nawwaf Aleisa, Andrews Damoah, Yingzhou Lu, and Xiaodong Qu
    HCI International, 2025 [PDF]

2023

  • Exploring AI Music Generation: A Review of Deep Learning Algorithms and Datasets for Undergraduate Researchers
    Isshin Yunoki, Guy Berreby, Nicholas D’Andrea, Yuhua Lu, and Xiaodong Qu
    HCI International, 2023

2022

Additional Applied AI

AI for Learning and Education

2026

  • Generative AI in Sports Management Education: A Systematic Review and Pilot Study
    Xinyu Liu and Xiaodong Qu
    HCI International, 2026 [PDF]

2025

2024

2018

  • EEG Markers of STEM Learning
    Xiaodong Qu, Yixin Sun, Robert Sekuler, and Timothy J. Hickey
    IEEE Frontiers in Education Conference, 2018 [PDF]

  • A Personalized Reading Coach Using Wearable EEG Sensors: A Pilot Study of Brainwave Learning Analytics
    Xiaodong Qu, Mercedes Hall, Yile Sun, Robert Sekuler, and Timothy J. Hickey
    International Conference on Computer Supported Education (CSEDU), 2018 [PDF]

Selected Mentored Student Publications

The following are selected publications and conference papers by students I mentored or supervised. I am not a coauthor on these papers unless indicated in the main publication sections above.

2026

2024

2023

2022

  • Too Fine or Too Coarse? The Goldilocks Composition of Data Complexity for Robust Left-Right Eye-Tracking Classifiers
    Abdelrahman Abdelmonsef and Brian Xiang
    KDD 2022 Undergraduate Consortium

  • EEG4Students: An Experimental Design for EEG Data Collection and Machine Learning Analysis
    Guangyao Dou and Zheng Zhou
    KDD 2022 Undergraduate Consortium

Students and Mentoring

I mentor undergraduate and graduate students through coursework, project-based research, independent study, funded research, and publication.

  • 50+ undergraduate and graduate students mentored

  • 15+ student-coauthored publications

  • 30+ Senior Capstone/Senior Design teams supervised

  • Funded undergraduate research at GW and Swarthmore

  • Student pathways from coursework to research, publication, and graduate study

My mentoring usually begins with a manageable technical problem: reproducing a baseline, preparing data, reviewing a focused body of literature, implementing an evaluation pipeline, or testing an existing method. As students gain experience, I encourage them to take more responsibility for research questions, model comparison, error analysis, writing, and presentation.

At Swarthmore, I mentored three full-time undergraduate summer researchers. Two students presented resulting work at the SIGKDD 2022 Undergraduate Consortium.

At GW, I have mentored students supported by the GW Undergraduate Research Award and the SEAS Summer Program for Undergraduate Research. This work has contributed to student-coauthored publications, conference presentations, and continuing research.

Students also move from my courses into longer-term research. One student progressed from Algorithms to Senior Design and independent AI-in-education research, coauthored three peer-reviewed papers at HCII, KDD, and CHI, and continued to a master’s program at the University of Chicago.

Teaching

I have taught Introduction to Computer Science, Algorithms, Machine Learning, Senior Capstone/Senior Design, and Machine Learning Student Research Project courses at The George Washington University and Swarthmore College.

My teaching emphasizes a progression from strong foundations to technical reasoning, project work, and increasing independence. In introductory courses, I use examples, guided practice, code tracing, debugging, and explanation to help students understand how programs work rather than simply produce working code. In Algorithms and Machine Learning, I ask students to compare alternatives, justify technical choices, evaluate results, and explain limitations.

Project-based courses give students experience with problems that do not have a single correct solution. I use milestones, feedback, demonstrations, and revision to help students take increasing responsibility for technical decisions and teamwork.

Generative AI has made independent technical reasoning even more important. I do not treat AI as a substitute for learning. Students should learn to evaluate AI-generated code and explanations, identify errors and limitations, and remain responsible for the reasoning and decisions behind their work.

News / Recent Highlights

2026

  • New BioNLP 2026 paper on agentic feature selection for epileptic seizure detection.

  • New HCI International papers on sleep EEG, accessible EEG game control, deployable neural directional control, transformer-based EEG analysis, and related human-centered AI research.

  • New KDD 2026 undergraduate research papers on NBA game prediction and 3D Gaussian Splatting.

2025

  • New IEEE ICDMW paper, “EEG EyeNet: Strong, Insightful Baselines for Eye-Movement Prediction from EEG.”

  • CHI Extended Abstract on generative AI tools in higher education.

  • GW Today: Gaming with Your Brain? That’s the Tip of the Iceberg — feature on brain-computer interfaces and neurological health research.

  • GW Today: GW Shines at 2025 AAAS Annual Meeting — feature including my research among GW experts participating in the AAAS Annual Meeting.

  • Student-coauthored KDD work on EEG-controlled directional games and custom-developed BCI game evaluation.

2024

  • Three student papers at the KDD 2024 Undergraduate Consortium, including work on generative AI for undergraduate research summarization and EEG data analysis.

  • HCI International 2024 research included work on EEG-based gaze prediction, eye tracking, and project-based machine-learning education.

2023

  • Two student papers at the KDD 2023 Undergraduate Consortium, including ViT2EEG and work reviewing machine-learning methods for EEG classification.

  • Joined the Department of Computer Science at The George Washington University as an Assistant Professor of Practice.

Service

  • Program Board Member and Session Chair, HCI International (HCII), 2023–2026.

  • Completed 120+ peer reviews for conferences and journals in machine learning, data mining, human-computer interaction, biomedical informatics, education, and related areas.

Contact